Coedit Large

🚀 CoEdIT-Large模型卡片

CoEdIT-Large模型通過在CoEdIT數據集上微調對應的google/flan-t5-large模型獲得。數據集的詳細信息可在我們的論文和倉庫中找到。

🚀 快速開始

我們提供了論文中所展示的模型。

基礎用法

from transformers import AutoTokenizer, T5ForConditionalGeneration

tokenizer = AutoTokenizer.from_pretrained("grammarly/coedit-large")
model = T5ForConditionalGeneration.from_pretrained("grammarly/coedit-large")
input_text = 'Fix grammatical errors in this sentence: When I grow up, I start to understand what he said is quite right.'
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids, max_length=256)
edited_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

✨ 主要特性

文本修訂任務

給定編輯指令和原始文本，我們的模型能夠生成編輯後的文本。

📚 詳細文檔

模型詳情

模型描述

• 語言（NLP）：英語
• 微調基礎模型：google/flan-t5-large

模型來源

• 倉庫：https://github.com/vipulraheja/coedit
• 論文：https://arxiv.org/abs/2305.09857

軟件

https://github.com/vipulraheja/coedit

📄 許可證

本模型使用CC BY-NC 4.0許可證。

數據集

• facebook/asset
• wi_locness
• GEM/wiki_auto_asset_turk
• discofuse
• zaemyung/IteraTeR_plus
• jfleg
• grammarly/coedit

評估指標

• sari
• bleu
• accuracy

示例

📝 引用

BibTeX

@article{raheja2023coedit,
      title={CoEdIT: Text Editing by Task-Specific Instruction Tuning}, 
      author={Vipul Raheja and Dhruv Kumar and Ryan Koo and Dongyeop Kang},
      year={2023},
      eprint={2305.09857},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

APA

Raheja, V., Kumar, D., Koo, R., & Kang, D. (2023). CoEdIT: Text Editing by Task-Specific Instruction Tuning. ArXiv. /abs/2305.09857

論文：CoEdIT: Text Editing by Task-Specific Instruction Tuning

作者：Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang